# CorentinJ/Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Repository: https://github.com/CorentinJ/Real-Time-Voice-Cloning
Canonical: https://ross.abutalabs.com/products/real-time-voice-cloning
Language: Python
License: NOASSERTION
License Family: other
Topics: deep-learning, pytorch, tensorflow, tts, voice-cloning, python
Last push: 2026-03-09T10:31:58+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 35, longevity 100
- inputs: {"age_days": 2656, "days_push": 177, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 60110, forks 9391 (observed 2026-08-28T04:12:18.780701+00:00)

## What it is
A Python implementation of the SV2TTS (Transfer Learning from Speaker Verification to Multispeaker TTS) framework that clones a voice from just a few seconds of audio and generates arbitrary speech in real time. It includes a GUI toolbox combining a speaker encoder, Tacotron synthesizer, and WaveRNN vocoder.

## Use cases
- clone a voice from a short audio sample
- generate speech in a specific person's voice from text
- real-time text-to-speech with custom voices
- experiment with SV2TTS and voice cloning research
- create a digital voice embedding from 5 seconds of audio

## When to choose
- you want a free, open-source voice cloning demo you can run locally
- you're studying or reproducing the SV2TTS paper pipeline
- you need real-time synthesis with a cloned voice on Windows or Linux

## When to avoid
- you need state-of-the-art audio quality - the author recommends newer projects like Chatterbox
- you want a production SaaS-grade TTS service
- you need a maintained, actively updated codebase

## Facets
- artifact type: library
- maturity: maintenance
- function: tts, speech-recognition, deep-learning, machine-learning
- domain: speech-processing, deep-learning, machine-learning
- platform: python, windows
- tags: voice-cloning, sv2tts, pytorch, tensorflow, vocoder, speaker-embedding, text-to-speech, audio, linux, gpu

## Member repositories
- CorentinJ/Real-Time-Voice-Cloning (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:18.780701+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:17:55.997961+00:00, confidence not recorded.
  - readme: https://github.com/CorentinJ/Real-Time-Voice-Cloning (fetched 2026-08-28T04:12:18.780701+00:00, sha 883732801959)
- Data as of 2026-08-30T08:39:29.467469+00:00.